Skip to content

TsukiNi22/ai-utils / skills/ai/rtk

Reduce to the minimum the tokens of a text, a command output, a report, a log or a program's output so it costs the least in an AI context - every human-readable part dropped (colors, ANSI, tables, rulers, banners, prose, repeated fields, absolute paths), only the signal kept in a compact machine-oriented form (legend once, one record per line, shared values written once, counters on one line), even if unreadable for a human - and design / implement an --rtk mode (flag + env var) on a program or script, like xstyle --rtk. Use whenever the user asks to compact / minify / compress a text or an output for an AI, to save tokens or context, for an "rtk" / "AI" / "token-optimized" output or mode, to add such a flag to a binary or a script, or to write a file only an AI will read.

Security report

Verified

Static analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.

Commit
6c7d8896b386f48b6ac1835868a776efd75c7fe0
Content hash
2c4092682b39d2f53892898cc5515b848f2ec178c682862492adbb946d170a1c
Scanned
2026-11-17
Scanner version
skillxone-scan-1.0.0
Policy version
0.1-draft
Decision
Every required check completed with no open blocking or medium findings.
Verification expires
2026-12-17

Findings (1 info)

  • infoINT-EXECUTABLE-SCRIPTscripts/compact.py:1

    The skill ships an executable script. Review it before allowing an agent to run it.

    """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""

    Suggested fix: None required. Informational.

    Report as false positive

Checks run

  • prompt-injection
  • dangerous-commands
  • credentials
  • network
  • file-access
  • integrity

Checks skipped

  • dependencies: No dependency manifest in the skill directory.
  • gitleaks: gitleaks is not installed on this host.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 319kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 197kUpdated Claude CodeCodexVerifiedInstall